Hey, I'm Sacha, co-founder at @Edgee
Over the last few months, we've been working on a problem we kept seeing in production AI systems:
LLM costs don't scale linearly with usage, they scale with context.
As teams add RAG, tool calls, long chat histories, memory, and guardrails, prompts become huge and token spend quickly becomes the main bottleneck.
So we built a token compression layer designed to run before inference.
Sqreen
Exciting launch! Congrats team
@paulblei Thanks a lot! Really appreciate it 🙌
If you get a chance to try Edgee, we’d love to hear what you think.
Thank you very much @paulblei . I must admit that the whole team is very excited as well. When we had the idea of using our edge computing skills to improve inference, I didn't have to insist for long to get buy-in, lol
Connectiviteam
Congrats!
@stanmassueras an honour to have your support. At @Edgee, we loooove @ElevenLabs 💪
@stanmassueras Thank you! We really appreciate the support 🙏
If you end up giving Edgee a try, we’d love to hear your feedback.
Tellers.ai
@picsoung @rguignar Would looove to see Edgee plugged into Tellers, that’s a perfect fit, especially with agent/tool-heavy workflows where context can grow fast.
If you’d like, happy to help you set it up or jump on a quick call to make integration smooth.
Tellers.ai
Congrats on the launch !
LLM's costs are going crazy here, I definitetly give it a try
You'll be welcome @angezanetti . We decided to build Edgee after talking with 50+ CTOs who started to struggle with token costs. Really exciting challenge, the team is sooo excited!